adding models

transforms/model_transforms.py

@@ -0,0 +1,75 @@
+import torch
+import torch.nn.functional as F
+from torchvision.transforms import v2
+
+
+class ResizeAndPadBatch:
+    """
+    Vectorized resize + zero pad for batched tensors.
+
+    Args:
+        imgs (Tensor): shape [B, C, H, W], pixel values in [0,1] or [0,255].
+        target_size (tuple): (target_h, target_w) final image shape.
+
+    Returns:
+        Tensor: shape [B, C, target_h, target_w]
+    """
+
+    def __init__(self, target_size=(640, 640), fill_value=0):
+        self.target_size = target_size
+        self.fill_value = fill_value
+        self.transform_stats = None
+
+    def __call__(self, imgs: torch.Tensor):
+
+        b, c, h, w = imgs.shape
+        target_h, target_w = self.target_size
+
+        # Compute scaling factors: preserve aspect ratio by same scale factor per image
+        scale_factors = float(
+            torch.minimum(torch.tensor(target_h / h), torch.tensor(target_w / w))
+        )
+
+        # New intermediate size
+        new_h = int(h * scale_factors)
+        new_w = int(w * scale_factors)
+
+        # Resize with bilinear interpolation
+        resized = F.interpolate(
+            imgs, size=(new_h, new_w), mode="bilinear", align_corners=False
+        )
+
+        # Calculate padding amounts (left, right, top, bottom)
+        pad_h = target_h - new_h
+        pad_w = target_w - new_w
+        pad_top = pad_h // 2
+        pad_bottom = pad_h - pad_top
+        pad_left = pad_w // 2
+        pad_right = pad_w - pad_left
+
+        # Apply padding (pad order in F.pad is [left, right, top, bottom])
+        padded = F.pad(
+            resized,
+            (pad_left, pad_right, pad_top, pad_bottom),
+            mode="constant",
+            value=self.fill_value,
+        )
+
+        self.transform_stats = {
+            "scale_factor": scale_factors,
+            'hw': [h,w],
+            "new_hw": [new_h, new_w],
+            "pad_TBLR": [pad_top,pad_bottom, pad_left, pad_right]
+        }
+
+        return padded
+
+
+clip_transforms = v2.Compose(
+    [
+        v2.Resize(size=(512, 512)),
+        v2.Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5)),
+    ]
+)
+
+det_transforms = v2.Compose([ResizeAndPadBatch(target_size=(640, 640))])